Recently, online social network data has become an important/interesting target of various analyses. In this talk, I will introduce some of our recent research on social network data analysis, such as early detection of new Twitter accounts that would be popular in future, classification of follow links in Twitter based on the purposes of the followers, and the classification of Twitter accounts based on their information publishing targets.

Keishi Tajima is a Professor at the School of Informatics of Kyoto University. His recent research interests include web information extraction, web search, online social network analysis, and user interface design for information access.